diff options
Diffstat (limited to 'arch/arm/oprofile')
| -rw-r--r-- | arch/arm/oprofile/Kconfig | 23 | ||||
| -rw-r--r-- | arch/arm/oprofile/Makefile | 6 | ||||
| -rw-r--r-- | arch/arm/oprofile/backtrace.c | 116 | ||||
| -rw-r--r-- | arch/arm/oprofile/common.c | 211 | ||||
| -rw-r--r-- | arch/arm/oprofile/op_arm_model.h | 31 | ||||
| -rw-r--r-- | arch/arm/oprofile/op_counter.h | 29 | ||||
| -rw-r--r-- | arch/arm/oprofile/op_model_xscale.c | 443 |
7 files changed, 91 insertions, 768 deletions
diff --git a/arch/arm/oprofile/Kconfig b/arch/arm/oprofile/Kconfig deleted file mode 100644 index 19d37730b66..00000000000 --- a/arch/arm/oprofile/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ - -menu "Profiling support" - depends on EXPERIMENTAL - -config PROFILING - bool "Profiling support (EXPERIMENTAL)" - help - Say Y here to enable the extended profiling support mechanisms used - by profilers such as OProfile. - - -config OPROFILE - tristate "OProfile system profiling (EXPERIMENTAL)" - depends on PROFILING - help - OProfile is a profiling system capable of profiling the - whole system, include the kernel, kernel modules, libraries, - and applications. - - If unsure, say N. - -endmenu - diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile index 6a94e54848f..b2215c61cdf 100644 --- a/arch/arm/oprofile/Makefile +++ b/arch/arm/oprofile/Makefile @@ -6,6 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprofilefs.o oprofile_stats.o \ timer_int.o ) -oprofile-y := $(DRIVER_OBJS) common.o backtrace.o -oprofile-$(CONFIG_CPU_XSCALE) += op_model_xscale.o +ifeq ($(CONFIG_HW_PERF_EVENTS),y) +DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o) +endif +oprofile-y := $(DRIVER_OBJS) common.o diff --git a/arch/arm/oprofile/backtrace.c b/arch/arm/oprofile/backtrace.c deleted file mode 100644 index 7c22c12618c..00000000000 --- a/arch/arm/oprofile/backtrace.c +++ /dev/null @@ -1,116 +0,0 @@ -/* - * Arm specific backtracing code for oprofile - * - * Copyright 2005 Openedhand Ltd. - * - * Author: Richard Purdie <rpurdie@openedhand.com> - * - * Based on i386 oprofile backtrace code by John Levon, David Smith - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/oprofile.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <asm/ptrace.h> -#include <asm/uaccess.h> - - -/* - * The registers we're interested in are at the end of the variable - * length saved register structure. The fp points at the end of this - * structure so the address of this struct is: - * (struct frame_tail *)(xxx->fp)-1 - */ -struct frame_tail { - struct frame_tail *fp; - unsigned long sp; - unsigned long lr; -} __attribute__((packed)); - - -#ifdef CONFIG_FRAME_POINTER -static struct frame_tail* kernel_backtrace(struct frame_tail *tail) -{ - oprofile_add_trace(tail->lr); - - /* frame pointers should strictly progress back up the stack - * (towards higher addresses) */ - if (tail >= tail->fp) - return NULL; - - return tail->fp-1; -} -#endif - -static struct frame_tail* user_backtrace(struct frame_tail *tail) -{ - struct frame_tail buftail[2]; - - /* Also check accessibility of one struct frame_tail beyond */ - if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) - return NULL; - if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) - return NULL; - - oprofile_add_trace(buftail[0].lr); - - /* frame pointers should strictly progress back up the stack - * (towards higher addresses) */ - if (tail >= buftail[0].fp) - return NULL; - - return buftail[0].fp-1; -} - -/* - * | | /\ Higher addresses - * | | - * --------------- stack base (address of current_thread_info) - * | thread info | - * . . - * | stack | - * --------------- saved regs->ARM_fp value if valid (frame_tail address) - * . . - * --------------- struct pt_regs stored on stack (struct pt_regs *) - * | | - * . . - * | | - * --------------- %esp - * | | - * | | \/ Lower addresses - * - * Thus, &pt_regs <-> stack base restricts the valid(ish) fp values - */ -static int valid_kernel_stack(struct frame_tail *tail, struct pt_regs *regs) -{ - unsigned long tailaddr = (unsigned long)tail; - unsigned long stack = (unsigned long)regs; - unsigned long stack_base = (stack & ~(THREAD_SIZE - 1)) + THREAD_SIZE; - - return (tailaddr > stack) && (tailaddr < stack_base); -} - -void arm_backtrace(struct pt_regs * const regs, unsigned int depth) -{ - struct frame_tail *tail; - - tail = ((struct frame_tail *) regs->ARM_fp) - 1; - - if (!user_mode(regs)) { - -#ifdef CONFIG_FRAME_POINTER - while (depth-- && tail && valid_kernel_stack(tail, regs)) { - tail = kernel_backtrace(tail); - } -#endif - return; - } - - while (depth-- && tail && !((unsigned long) tail & 3)) - tail = user_backtrace(tail); -} diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 6f833358cd0..99c63d4b6af 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -2,169 +2,132 @@ * @file common.c * * @remark Copyright 2004 Oprofile Authors + * @remark Copyright 2010 ARM Ltd. * @remark Read the file COPYING * * @author Zwane Mwaikambo + * @author Will Deacon [move to perf] */ +#include <linux/cpumask.h> #include <linux/init.h> +#include <linux/mutex.h> #include <linux/oprofile.h> -#include <linux/errno.h> +#include <linux/perf_event.h> +#include <linux/platform_device.h> #include <linux/slab.h> -#include <linux/sysdev.h> -#include <linux/mutex.h> +#include <asm/stacktrace.h> +#include <linux/uaccess.h> -#include "op_counter.h" -#include "op_arm_model.h" +#include <asm/perf_event.h> +#include <asm/ptrace.h> -static struct op_arm_model_spec *op_arm_model; -static int op_arm_enabled; -static DEFINE_MUTEX(op_arm_mutex); +#ifdef CONFIG_HW_PERF_EVENTS -struct op_counter_config *counter_config; +/* + * OProfile has a curious naming scheme for the ARM PMUs, but they are + * part of the user ABI so we need to map from the perf PMU name for + * supported PMUs. + */ +static struct op_perf_name { + char *perf_name; + char *op_name; +} op_perf_name_map[] = { + { "xscale1", "arm/xscale1" }, + { "xscale1", "arm/xscale2" }, + { "v6", "arm/armv6" }, + { "v6mpcore", "arm/mpcore" }, + { "ARMv7 Cortex-A8", "arm/armv7" }, + { "ARMv7 Cortex-A9", "arm/armv7-ca9" }, +}; -static int op_arm_create_files(struct super_block *sb, struct dentry *root) +char *op_name_from_perf_id(void) { - unsigned int i; - - for (i = 0; i < op_arm_model->num_counters; i++) { - struct dentry *dir; - char buf[4]; - - snprintf(buf, sizeof buf, "%d", i); - dir = oprofilefs_mkdir(sb, root, buf); - oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); - oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event); - oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count); - oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); - oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); - oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); + int i; + struct op_perf_name names; + const char *perf_name = perf_pmu_name(); + + for (i = 0; i < ARRAY_SIZE(op_perf_name_map); ++i) { + names = op_perf_name_map[i]; + if (!strcmp(names.perf_name, perf_name)) + return names.op_name; } - return 0; -} - -static int op_arm_setup(void) -{ - int ret; - - spin_lock(&oprofilefs_lock); - ret = op_arm_model->setup_ctrs(); - spin_unlock(&oprofilefs_lock); - return ret; + return NULL; } +#endif -static int op_arm_start(void) +static int report_trace(struct stackframe *frame, void *d) { - int ret = -EBUSY; + unsigned int *depth = d; - mutex_lock(&op_arm_mutex); - if (!op_arm_enabled) { - ret = op_arm_model->start(); - op_arm_enabled = !ret; + if (*depth) { + oprofile_add_trace(frame->pc); + (*depth)--; } - mutex_unlock(&op_arm_mutex); - return ret; -} -static void op_arm_stop(void) -{ - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) - op_arm_model->stop(); - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); + return *depth == 0; } -#ifdef CONFIG_PM -static int op_arm_suspend(struct sys_device *dev, pm_message_t state) -{ - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) - op_arm_model->stop(); - mutex_unlock(&op_arm_mutex); - return 0; -} +/* + * The registers we're interested in are at the end of the variable + * length saved register structure. The fp points at the end of this + * structure so the address of this struct is: + * (struct frame_tail *)(xxx->fp)-1 + */ +struct frame_tail { + struct frame_tail *fp; + unsigned long sp; + unsigned long lr; +} __attribute__((packed)); -static int op_arm_resume(struct sys_device *dev) +static struct frame_tail* user_backtrace(struct frame_tail *tail) { - mutex_lock(&op_arm_mutex); - if (op_arm_enabled && op_arm_model->start()) - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); - return 0; -} + struct frame_tail buftail[2]; -static struct sysdev_class oprofile_sysclass = { - set_kset_name("oprofile"), - .resume = op_arm_resume, - .suspend = op_arm_suspend, -}; + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) + return NULL; + if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) + return NULL; -static struct sys_device device_oprofile = { - .id = 0, - .cls = &oprofile_sysclass, -}; + oprofile_add_trace(buftail[0].lr); -static int __init init_driverfs(void) -{ - int ret; - - if (!(ret = sysdev_class_register(&oprofile_sysclass))) - ret = sysdev_register(&device_oprofile); + /* frame pointers should strictly progress back up the stack + * (towards higher addresses) */ + if (tail + 1 >= buftail[0].fp) + return NULL; - return ret; + return buftail[0].fp-1; } -static void exit_driverfs(void) +static void arm_backtrace(struct pt_regs * const regs, unsigned int depth) { - sysdev_unregister(&device_oprofile); - sysdev_class_unregister(&oprofile_sysclass); + struct frame_tail *tail = ((struct frame_tail *) regs->ARM_fp) - 1; + + if (!user_mode(regs)) { + struct stackframe frame; + frame.fp = regs->ARM_fp; + frame.sp = regs->ARM_sp; + frame.lr = regs->ARM_lr; + frame.pc = regs->ARM_pc; + walk_stackframe(&frame, report_trace, &depth); + return; + } + + while (depth-- && tail && !((unsigned long) tail & 3)) + tail = user_backtrace(tail); } -#else -#define init_driverfs() do { } while (0) -#define exit_driverfs() do { } while (0) -#endif /* CONFIG_PM */ int __init oprofile_arch_init(struct oprofile_operations *ops) { - struct op_arm_model_spec *spec = NULL; - int ret = -ENODEV; - -#ifdef CONFIG_CPU_XSCALE - spec = &op_xscale_spec; -#endif + /* provide backtrace support also in timer mode: */ + ops->backtrace = arm_backtrace; - if (spec) { - ret = spec->init(); - if (ret < 0) - return ret; - - counter_config = kcalloc(spec->num_counters, sizeof(struct op_counter_config), - GFP_KERNEL); - if (!counter_config) - return -ENOMEM; - - op_arm_model = spec; - init_driverfs(); - ops->create_files = op_arm_create_files; - ops->setup = op_arm_setup; - ops->shutdown = op_arm_stop; - ops->start = op_arm_start; - ops->stop = op_arm_stop; - ops->cpu_type = op_arm_model->name; - ops->backtrace = arm_backtrace; - printk(KERN_INFO "oprofile: using %s\n", spec->name); - } - - return ret; + return oprofile_perf_init(ops); } void oprofile_arch_exit(void) { - if (op_arm_model) { - exit_driverfs(); - op_arm_model = NULL; - } - kfree(counter_config); + oprofile_perf_exit(); } diff --git a/arch/arm/oprofile/op_arm_model.h b/arch/arm/oprofile/op_arm_model.h deleted file mode 100644 index 38c6ad15854..00000000000 --- a/arch/arm/oprofile/op_arm_model.h +++ /dev/null @@ -1,31 +0,0 @@ -/** - * @file op_arm_model.h - * interface to ARM machine specific operations - * - * @remark Copyright 2004 Oprofile Authors - * @remark Read the file COPYING - * - * @author Zwane Mwaikambo - */ - -#ifndef OP_ARM_MODEL_H -#define OP_ARM_MODEL_H - -struct op_arm_model_spec { - int (*init)(void); - unsigned int num_counters; - int (*setup_ctrs)(void); - int (*start)(void); - void (*stop)(void); - char *name; -}; - -#ifdef CONFIG_CPU_XSCALE -extern struct op_arm_model_spec op_xscale_spec; -#endif - -extern void arm_backtrace(struct pt_regs * const regs, unsigned int depth); - -extern int __init op_arm_init(struct oprofile_operations *ops, struct op_arm_model_spec *spec); -extern void op_arm_exit(void); -#endif /* OP_ARM_MODEL_H */ diff --git a/arch/arm/oprofile/op_counter.h b/arch/arm/oprofile/op_counter.h deleted file mode 100644 index 8c5351d751c..00000000000 --- a/arch/arm/oprofile/op_counter.h +++ /dev/null @@ -1,29 +0,0 @@ -/** - * @file op_counter.h - * - * @remark Copyright 2004 Oprofile Authors - * @remark Read the file COPYING - * - * @author Zwane Mwaikambo - */ - -#ifndef OP_COUNTER_H -#define OP_COUNTER_H - -#define OP_MAX_COUNTER 5 - -/* Per performance monitor configuration as set via - * oprofilefs. - */ -struct op_counter_config { - unsigned long count; - unsigned long enabled; - unsigned long event; - unsigned long unit_mask; - unsigned long kernel; - unsigned long user; -}; - -extern struct op_counter_config *counter_config; - -#endif /* OP_COUNTER_H */ diff --git a/arch/arm/oprofile/op_model_xscale.c b/arch/arm/oprofile/op_model_xscale.c deleted file mode 100644 index e0f0b320d76..00000000000 --- a/arch/arm/oprofile/op_model_xscale.c +++ /dev/null @@ -1,443 +0,0 @@ -/** - * @file op_model_xscale.c - * XScale Performance Monitor Driver - * - * @remark Copyright 2000-2004 Deepak Saxena <dsaxena@mvista.com> - * @remark Copyright 2000-2004 MontaVista Software Inc - * @remark Copyright 2004 Dave Jiang <dave.jiang@intel.com> - * @remark Copyright 2004 Intel Corporation - * @remark Copyright 2004 Zwane Mwaikambo <zwane@arm.linux.org.uk> - * @remark Copyright 2004 OProfile Authors - * - * @remark Read the file COPYING - * - * @author Zwane Mwaikambo - */ - -/* #define DEBUG */ -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/oprofile.h> -#include <linux/interrupt.h> -#include <asm/irq.h> -#include <asm/system.h> - -#include "op_counter.h" -#include "op_arm_model.h" - -#define PMU_ENABLE 0x001 /* Enable counters */ -#define PMN_RESET 0x002 /* Reset event counters */ -#define CCNT_RESET 0x004 /* Reset clock counter */ -#define PMU_RESET (CCNT_RESET | PMN_RESET) -#define PMU_CNT64 0x008 /* Make CCNT count every 64th cycle */ - -/* TODO do runtime detection */ -#ifdef CONFIG_ARCH_IOP310 -#define XSCALE_PMU_IRQ IRQ_XS80200_PMU -#endif -#ifdef CONFIG_ARCH_IOP321 -#define XSCALE_PMU_IRQ IRQ_IOP321_CORE_PMU -#endif -#ifdef CONFIG_ARCH_IOP331 -#define XSCALE_PMU_IRQ IRQ_IOP331_CORE_PMU -#endif -#ifdef CONFIG_ARCH_PXA -#define XSCALE_PMU_IRQ IRQ_PMU -#endif - -/* - * Different types of events that can be counted by the XScale PMU - * as used by Oprofile userspace. Here primarily for documentation - * purposes. - */ - -#define EVT_ICACHE_MISS 0x00 -#define EVT_ICACHE_NO_DELIVER 0x01 -#define EVT_DATA_STALL 0x02 -#define EVT_ITLB_MISS 0x03 -#define EVT_DTLB_MISS 0x04 -#define EVT_BRANCH 0x05 -#define EVT_BRANCH_MISS 0x06 -#define EVT_INSTRUCTION 0x07 -#define EVT_DCACHE_FULL_STALL 0x08 -#define EVT_DCACHE_FULL_STALL_CONTIG 0x09 -#define EVT_DCACHE_ACCESS 0x0A -#define EVT_DCACHE_MISS 0x0B -#define EVT_DCACE_WRITE_BACK 0x0C -#define EVT_PC_CHANGED 0x0D -#define EVT_BCU_REQUEST 0x10 -#define EVT_BCU_FULL 0x11 -#define EVT_BCU_DRAIN 0x12 -#define EVT_BCU_ECC_NO_ELOG 0x14 -#define EVT_BCU_1_BIT_ERR 0x15 -#define EVT_RMW 0x16 -/* EVT_CCNT is not hardware defined */ -#define EVT_CCNT 0xFE -#define EVT_UNUSED 0xFF - -struct pmu_counter { - volatile unsigned long ovf; - unsigned long reset_counter; -}; - -enum { CCNT, PMN0, PMN1, PMN2, PMN3, MAX_COUNTERS }; - -static struct pmu_counter results[MAX_COUNTERS]; - -/* - * There are two versions of the PMU in current XScale processors - * with differing register layouts and number of performance counters. - * e.g. IOP321 is xsc1 whilst IOP331 is xsc2. - * We detect which register layout to use in xscale_detect_pmu() - */ -enum { PMU_XSC1, PMU_XSC2 }; - -struct pmu_type { - int id; - char *name; - int num_counters; - unsigned int int_enable; - unsigned int cnt_ovf[MAX_COUNTERS]; - unsigned int int_mask[MAX_COUNTERS]; -}; - -static struct pmu_type pmu_parms[] = { - { - .id = PMU_XSC1, - .name = "arm/xscale1", - .num_counters = 3, - .int_mask = { [PMN0] = 0x10, [PMN1] = 0x20, - [CCNT] = 0x40 }, - .cnt_ovf = { [CCNT] = 0x400, [PMN0] = 0x100, - [PMN1] = 0x200}, - }, - { - .id = PMU_XSC2, - .name = "arm/xscale2", - .num_counters = 5, - .int_mask = { [CCNT] = 0x01, [PMN0] = 0x02, - [PMN1] = 0x04, [PMN2] = 0x08, - [PMN3] = 0x10 }, - .cnt_ovf = { [CCNT] = 0x01, [PMN0] = 0x02, - [PMN1] = 0x04, [PMN2] = 0x08, - [PMN3] = 0x10 }, - }, -}; - -static struct pmu_type *pmu; - -static void write_pmnc(u32 val) -{ - if (pmu->id == PMU_XSC1) { - /* upper 4bits and 7, 11 are write-as-0 */ - val &= 0xffff77f; - __asm__ __volatile__ ("mcr p14, 0, %0, c0, c0, 0" : : "r" (val)); - } else { - /* bits 4-23 are write-as-0, 24-31 are write ignored */ - val &= 0xf; - __asm__ __volatile__ ("mcr p14, 0, %0, c0, c1, 0" : : "r" (val)); - } -} - -static u32 read_pmnc(void) -{ - u32 val; - - if (pmu->id == PMU_XSC1) - __asm__ __volatile__ ("mrc p14, 0, %0, c0, c0, 0" : "=r" (val)); - else { - __asm__ __volatile__ ("mrc p14, 0, %0, c0, c1, 0" : "=r" (val)); - /* bits 1-2 and 4-23 are read-unpredictable */ - val &= 0xff000009; - } - - return val; -} - -static u32 __xsc1_read_counter(int counter) -{ - u32 val = 0; - - switch (counter) { - case CCNT: - __asm__ __volatile__ ("mrc p14, 0, %0, c1, c0, 0" : "=r" (val)); - break; - case PMN0: - __asm__ __volatile__ ("mrc p14, 0, %0, c2, c0, 0" : "=r" (val)); - break; - case PMN1: - __asm__ __volatile__ ("mrc p14, 0, %0, c3, c0, 0" : "=r" (val)); - break; - } - return val; -} - -static u32 __xsc2_read_counter(int counter) -{ - u32 val = 0; - - switch (counter) { - case CCNT: - __asm__ __volatile__ ("mrc p14, 0, %0, c1, c1, 0" : "=r" (val)); - break; - case PMN0: - __asm__ __volatile__ ("mrc p14, 0, %0, c0, c2, 0" : "=r" (val)); - break; - case PMN1: - __asm__ __volatile__ ("mrc p14, 0, %0, c1, c2, 0" : "=r" (val)); - break; - case PMN2: - __asm__ __volatile__ ("mrc p14, 0, %0, c2, c2, 0" : "=r" (val)); - break; - case PMN3: - __asm__ __volatile__ ("mrc p14, 0, %0, c3, c2, 0" : "=r" (val)); - break; - } - return val; -} - -static u32 read_counter(int counter) -{ - u32 val; - - if (pmu->id == PMU_XSC1) - val = __xsc1_read_counter(counter); - else - val = __xsc2_read_counter(counter); - - return val; -} - -static void __xsc1_write_counter(int counter, u32 val) -{ - switch (counter) { - case CCNT: - __asm__ __volatile__ ("mcr p14, 0, %0, c1, c0, 0" : : "r" (val)); - break; - case PMN0: - __asm__ __volatile__ ("mcr p14, 0, %0, c2, c0, 0" : : "r" (val)); - break; - case PMN1: - __asm__ __volatile__ ("mcr p14, 0, %0, c3, c0, 0" : : "r" (val)); - break; - } -} - -static void __xsc2_write_counter(int counter, u32 val) -{ - switch (counter) { - case CCNT: - __asm__ __volatile__ ("mcr p14, 0, %0, c1, c1, 0" : : "r" (val)); - break; - case PMN0: - __asm__ __volatile__ ("mcr p14, 0, %0, c0, c2, 0" : : "r" (val)); - break; - case PMN1: - __asm__ __volatile__ ("mcr p14, 0, %0, c1, c2, 0" : : "r" (val)); - break; - case PMN2: - __asm__ __volatile__ ("mcr p14, 0, %0, c2, c2, 0" : : "r" (val)); - break; - case PMN3: - __asm__ __volatile__ ("mcr p14, 0, %0, c3, c2, 0" : : "r" (val)); - break; - } -} - -static void write_counter(int counter, u32 val) -{ - if (pmu->id == PMU_XSC1) - __xsc1_write_counter(counter, val); - else - __xsc2_write_counter(counter, val); -} - -static int xscale_setup_ctrs(void) -{ - u32 evtsel, pmnc; - int i; - - for (i = CCNT; i < MAX_COUNTERS; i++) { - if (counter_config[i].enabled) - continue; - - counter_config[i].event = EVT_UNUSED; - } - - switch (pmu->id) { - case PMU_XSC1: - pmnc = (counter_config[PMN1].event << 20) | (counter_config[PMN0].event << 12); - pr_debug("xscale_setup_ctrs: pmnc: %#08x\n", pmnc); - write_pmnc(pmnc); - break; - - case PMU_XSC2: - evtsel = counter_config[PMN0].event | (counter_config[PMN1].event << 8) | - (counter_config[PMN2].event << 16) | (counter_config[PMN3].event << 24); - - pr_debug("xscale_setup_ctrs: evtsel %#08x\n", evtsel); - __asm__ __volatile__ ("mcr p14, 0, %0, c8, c1, 0" : : "r" (evtsel)); - break; - } - - for (i = CCNT; i < MAX_COUNTERS; i++) { - if (counter_config[i].event == EVT_UNUSED) { - counter_config[i].event = 0; - pmu->int_enable &= ~pmu->int_mask[i]; - continue; - } - - results[i].reset_counter = counter_config[i].count; - write_counter(i, -(u32)counter_config[i].count); - pmu->int_enable |= pmu->int_mask[i]; - pr_debug("xscale_setup_ctrs: counter%d %#08x from %#08lx\n", i, - read_counter(i), counter_config[i].count); - } - - return 0; -} - -static void inline __xsc1_check_ctrs(void) -{ - int i; - u32 pmnc = read_pmnc(); - - /* NOTE: there's an A stepping errata that states if an overflow */ - /* bit already exists and another occurs, the previous */ - /* Overflow bit gets cleared. There's no workaround. */ - /* Fixed in B stepping or later */ - - /* Write the value back to clear the overflow flags. Overflow */ - /* flags remain in pmnc for use below */ - write_pmnc(pmnc & ~PMU_ENABLE); - - for (i = CCNT; i <= PMN1; i++) { - if (!(pmu->int_mask[i] & pmu->int_enable)) - continue; - - if (pmnc & pmu->cnt_ovf[i]) - results[i].ovf++; - } -} - -static void inline __xsc2_check_ctrs(void) -{ - int i; - u32 flag = 0, pmnc = read_pmnc(); - - pmnc &= ~PMU_ENABLE; - write_pmnc(pmnc); - - /* read overflow flag register */ - __asm__ __volatile__ ("mrc p14, 0, %0, c5, c1, 0" : "=r" (flag)); - - for (i = CCNT; i <= PMN3; i++) { - if (!(pmu->int_mask[i] & pmu->int_enable)) - continue; - - if (flag & pmu->cnt_ovf[i]) - results[i].ovf++; - } - - /* writeback clears overflow bits */ - __asm__ __volatile__ ("mcr p14, 0, %0, c5, c1, 0" : : "r" (flag)); -} - -static irqreturn_t xscale_pmu_interrupt(int irq, void *arg, struct pt_regs *regs) -{ - int i; - u32 pmnc; - - if (pmu->id == PMU_XSC1) - __xsc1_check_ctrs(); - else - __xsc2_check_ctrs(); - - for (i = CCNT; i < MAX_COUNTERS; i++) { - if (!results[i].ovf) - continue; - - write_counter(i, -(u32)results[i].reset_counter); - oprofile_add_sample(regs, i); - results[i].ovf--; - } - - pmnc = read_pmnc() | PMU_ENABLE; - write_pmnc(pmnc); - - return IRQ_HANDLED; -} - -static void xscale_pmu_stop(void) -{ - u32 pmnc = read_pmnc(); - - pmnc &= ~PMU_ENABLE; - write_pmnc(pmnc); - - free_irq(XSCALE_PMU_IRQ, results); -} - -static int xscale_pmu_start(void) -{ - int ret; - u32 pmnc = read_pmnc(); - - ret = request_irq(XSCALE_PMU_IRQ, xscale_pmu_interrupt, SA_INTERRUPT, - "XScale PMU", (void *)results); - - if (ret < 0) { - printk(KERN_ERR "oprofile: unable to request IRQ%d for XScale PMU\n", - XSCALE_PMU_IRQ); - return ret; - } - - if (pmu->id == PMU_XSC1) - pmnc |= pmu->int_enable; - else { - __asm__ __volatile__ ("mcr p14, 0, %0, c4, c1, 0" : : "r" (pmu->int_enable)); - pmnc &= ~PMU_CNT64; - } - - pmnc |= PMU_ENABLE; - write_pmnc(pmnc); - pr_debug("xscale_pmu_start: pmnc: %#08x mask: %08x\n", pmnc, pmu->int_enable); - return 0; -} - -static int xscale_detect_pmu(void) -{ - int ret = 0; - u32 id; - - id = (read_cpuid(CPUID_ID) >> 13) & 0x7; - - switch (id) { - case 1: - pmu = &pmu_parms[PMU_XSC1]; - break; - case 2: - pmu = &pmu_parms[PMU_XSC2]; - break; - default: - ret = -ENODEV; - break; - } - - if (!ret) { - op_xscale_spec.name = pmu->name; - op_xscale_spec.num_counters = pmu->num_counters; - pr_debug("xscale_detect_pmu: detected %s PMU\n", pmu->name); - } - - return ret; -} - -struct op_arm_model_spec op_xscale_spec = { - .init = xscale_detect_pmu, - .setup_ctrs = xscale_setup_ctrs, - .start = xscale_pmu_start, - .stop = xscale_pmu_stop, -}; - |
